Yesian Rohn | Xingsong Ye

I am a Master's student in Computer Science at Fudan University, under the supervision of Prof. Zhineng Chen in the FVL Group. Before that, nothing had happened.

I am currently focused on projects involving OCR, MultiModal, AIGC (C means Comedy). Please connect and collaborate with me to explore the potential of these fields and leverage them to make a positive impact on exciting computer science projects!

Email  /  CV  /  Google Scholar  /  OpenReview  /  Github  /  Bilibili  /  Zhihu

We introduce a novel safety alignment challenge called Safe Inputs but Unsafe Output (SIUO) to evaluate cross-modality safety alignment. Specifically, it considers cases where single modalities are safe independently but could potentially lead to unsafe or unethical outputs when combined.

We introduce CL2S, an innovative image dehazing network that overcomes limitations of DM2F (baseline) by trying sine functions, as validated through systematic ablation experiments.

We enhance LLMs' understanding of Chinese slang using curated datasets and advanced techniques, introducing DuanzAI and its application in the ChatDAI chatbot.

• Fudan Excellent League Member, Spring 2024.
• Third-class in Fudan Guanghua Social and Academic Practice Competition, Winter 2023.
• Fudan Outstanding Student, Autumn 2023.
• Alibaba Cloud Annual Geek of Greencode, Winter 2022.

• Jinrirencai Scholarship, Spring 2024.
• First-class Scholarship of Fudan University (Graduate Scholarship), Spring 2024.
• Duckbill Scholarship (Endowed Scholarship of Fudan University), Autumn 2023.
• Pujiang Innovation Forum Volunteer Nickname Bid-Winning Award, Summer 2023.
• Third-class Scholarship of Fudan University, Autumn 2022.

Teaching / TA

• Artificial Intelligence A (2024 Spring)
• Set Theory and Graph Theory (2024 Autumn)
• Practical Exploration of Frontiers in Artificial Intelligence(G) (2024 Autumn)

Referee / Reviewer

• TWTK (2023)